A Stacked Machine and Deep Learning-Based Approach for Analysing Electricity Theft in Smart Grids

Abstract

The role of electricity theft detection (ETD) is critical to maintain cost-efficiency in smart grids. However, existing methods for theft detection can struggle to handle large electricity consumption datasets because of missing values, data variance and nonlinear data relationship problems, and there is a lack of integrated infrastructure for coordinating electricity load data analysis procedures. To help address these problems, a simple yet effective ETD model is developed. Three modules are combined into the proposed model. The first module deploys a combination of data imputation, outlier handling, normalization and class balancing algorithms, to enhance the time series characteristics and generate better quality data for improved training and learning by the classifiers. Three different machine learning (ML) methods, which are uncorrelated and skillful on the problem in different ways, are employed as the base learning model. Finally, a recently developed deep learning approach, namely a temporal convolutional network (TCN), is used to ensemble the outputs of the ML algorithms for improved classification accuracy. Experimental results confirm that the proposed framework yields a highly-accurate, robust classification performance, in comparison to other well-established machine and deep learning models and thus can be a practical tool for electricity theft detection in industrial applications.

RFE Based Feature Selection and KNNOR Based Data Balancing for Electricity Theft Detection Using BiLSTM-LogitBoost Stacking Ensemble Model

“…In this article, we choose to develop stacking ensemble model for ETD in SGs. The reason is that it is the best strategy among different modern approaches based on the wining of numerous Kaggle and Netflix competitions for solving classification problems [68]. Stacking ensemble is a robust approach in which we can place multiple classifiers at level-0 (also called base classifiers) and a single classifier at level-1 (also called meta classifier) to obtain higher prediction performance.…”

Employing a Machine Learning Boosting Classifiers Based Stacking Ensemble Model for Detecting Non Technical Losses in Smart Grids

“…We selected the stacking ensemble strategy in this article for the reason that stacking ensemble strategy outperforms the techniques employed in the literature. Moreover, stacking ensembles recently won many data science competitions specifically Kaggle and Netflix for classification problems [26]. Hence, stacking ensembles are considered the best of all classifiers.…”

“…Therefore, to conduct a fair as well as extensive evaluation of our proposed MLBCSM, accuracy, ROC-AUC, F1 score, FPR, FNR, precision, recall, and PR-AUC are considered. The calculation of all the selected metrics is based on the confusion matrix [26] that consists of four unique values, which are defined below.…”

On the effect of sampling frequency on the electricity theft detection performance

“…[12], emphasise the effect of the unbalanced characteristic of the datasets in the electricity theft detection problem. In another research work on the SGCC dataset, the authors used a combination of machine learning and deep learning approaches to enhance consumption time‐series [13].…”